๐ŸŒ™ Sandman Tales v2

AI-Powered Multilingual Bedtime Stories

Team ClawCutters โ€” Mistral Worldwide Hackathon 2026

Technical 20% Creativity 20% Usefulness 20% Demo 20% Track Alignment 20%
๐ŸŽฏ Usefulness

The Quiet Crisis

27.6%
of Australians were born overseas โ€” ABS Census

Millions of kids grow up hearing a second language at home.
But that language fades as English takes over at school.

"I don't want Sophie to forget French. It's who we are." โ€” Sophie's mum
๐Ÿ’ก Creativity

Sandman Tales

Bedtime stories that keep heritage languages alive


๐ŸŽค
Parent speaks
in English
โ†’
๐Ÿ•ท๏ธ
AI writes story
in child's heritage language
โ†’
๐Ÿ”Š
Child listens
to personalised bedtime tale

10 languages ยท Personalised with child's name ยท Watercolour illustrations ยท Three audio layers

๐Ÿ’ก Creativity

Meet the Team

Six AI agents inspired by cultural mythology

๐ŸŒณ Papa Bois
Orchestrator

๐Ÿ•ท๏ธ Anansi
Storyteller

๐Ÿ—ฃ๏ธ Ogma
Language Guardian

๐Ÿ™ Devi
Voice & Audio

๐Ÿฆ† Firefly
Builder

๐Ÿญ Jerry
Concierge

โš™๏ธ Technical

System Architecture

%%{init: {"theme": "dark", "themeVariables": {"primaryColor": "#a78bfa", "primaryTextColor": "#e2e8f0", "primaryBorderColor": "#818cf8", "lineColor": "#f59e0b", "secondaryColor": "#1e1b4b", "tertiaryColor": "#0f172a", "fontSize": "14px"}}}%% graph TB subgraph CLIENT["๐Ÿ–ฅ๏ธ Frontend โ€” React + Vite"] UI["Story Creator
Story Player
Story Library
Voice Picker"] end subgraph BACKEND["โšก Backend โ€” FastAPI on Railway"] API["REST API + WebSocket"] CACHE["Prompt Cache
SHA-256 Dedup"] ORCH["๐ŸŒณ Papa Bois
Orchestrator"] end subgraph MISTRAL["๐Ÿค– Mistral AI"] AGENTS_API["Agents API
Conversations + Handoffs"] LARGE["Mistral Large 3
Story Generation"] VOX["Voxtral
Speech-to-Text"] end subgraph ELEVEN["๐Ÿ”Š ElevenLabs"] STT["Scribe v1 โ€” STT"] TTS["Multilingual v2 โ€” TTS"] STREAM["WebSocket Streaming"] SFX["Sound Effects"] MUSIC["Music Compose"] VOICES["Voices API"] EA["ElevenAgents"] end subgraph STORAGE["๐Ÿ’พ Storage"] TURSO["Turso
SQLite Cloud
Tokyo Region"] IMAGEN["Google Gemini Image Generation
Illustrations"] end UI -->|HTTPS| API API --> CACHE CACHE -->|cache miss| ORCH ORCH -->|delegates| AGENTS_API AGENTS_API --> LARGE ORCH -->|dual STT| VOX ORCH -->|dual STT| STT ORCH -->|narrate| TTS ORCH -->|stream| STREAM ORCH -->|ambient| SFX ORCH -->|lullaby| MUSIC ORCH -->|browse| VOICES ORCH -->|chat| EA ORCH -->|illustrate| IMAGEN API -->|persist| TURSO CACHE -->|dedup| TURSO style CLIENT fill:#1e1b4b,stroke:#818cf8,color:#e2e8f0 style BACKEND fill:#1e1b4b,stroke:#f59e0b,color:#e2e8f0 style MISTRAL fill:#2d1f5e,stroke:#a78bfa,color:#e2e8f0 style ELEVEN fill:#1b2e1b,stroke:#34d399,color:#e2e8f0 style STORAGE fill:#2e1f1b,stroke:#f59e0b,color:#e2e8f0
โš™๏ธ Technical

Agent Pipeline โ€” Story Creation Flow

%%{init: {"theme": "dark", "themeVariables": {"primaryColor": "#a78bfa", "primaryTextColor": "#e2e8f0", "lineColor": "#f59e0b", "fontSize": "13px"}}}%% sequenceDiagram participant P as ๐ŸŽค Parent participant O as ๐Ÿ—ฃ๏ธ Ogma
Language Guardian participant C as ๐Ÿ“‹ Cache participant PB as ๐ŸŒณ Papa Bois
Orchestrator participant G as ๐Ÿ›ก๏ธ Guardrail participant A as ๐Ÿ•ท๏ธ Anansi
Storyteller participant D as ๐Ÿ™ Devi
Voice/Audio participant F as ๐Ÿฆ† Firefly
Builder P->>O: Voice input (mic) activate O O->>O: ElevenLabs STT (Scribe v1) O->>O: Mistral Voxtral STT O->>O: Cross-validate + detect language O-->>C: Transcribed text + language deactivate O C->>C: SHA-256 hash check alt Cache Hit C-->>P: Return cached story else Cache Miss C->>PB: Forward to orchestrator activate PB PB->>G: Content safety check G-->>PB: โœ… Safe PB->>A: Delegate via Agents API activate A A->>A: Mistral Large 3 generates story A->>A: Split into 6 scenes A-->>PB: Story JSON (6 scenes) deactivate A par Audio Generation PB->>D: Generate narration (TTS) PB->>D: Generate SFX per scene PB->>D: Compose lullaby and Illustration PB->>F: Generate 6 scene images F->>F: Gemini Image Generation watercolours end D-->>PB: ๐Ÿ”Š Audio (narration + SFX + lullaby) F-->>PB: ๐ŸŽจ 6 illustrations PB-->>C: Store in Turso deactivate PB C-->>P: Complete story with media end
โš™๏ธ Technical๐Ÿ† Track Alignment

Mistral Agents API โ€” Orchestration Detail

%%{init: {"theme": "dark", "themeVariables": {"primaryColor": "#f59e0b", "primaryTextColor": "#e2e8f0", "lineColor": "#a78bfa", "fontSize": "13px"}}}%% graph TB subgraph PAPA["๐ŸŒณ Papa Bois โ€” Orchestrator Agent"] direction TB CONV["Conversations API
Multi-turn context"] HAND["Handoffs
Agent delegation"] TOOLS["Function Calling
4 ElevenLabs tools bound"] end subgraph ANANSI["๐Ÿ•ท๏ธ Anansi โ€” Storyteller Agent"] direction TB ML3["Mistral Large 3"] JSON["JSON Mode
Structured scene output"] CULT["Cultural sensitivity
Language-aware prompts"] end subgraph DEVI_TOOLS["๐Ÿ™ Devi โ€” Bound Function Tools"] TTS_F["generate_tts()"] SFX_F["generate_sound_effect()"] LUL_F["compose_lullaby()"] SEARCH["search_cultural_context()
via Tavily"] end subgraph OGMA_DUAL["๐Ÿ—ฃ๏ธ Ogma โ€” Dual STT"] EL_STT["ElevenLabs Scribe v1"] VOX_STT["Mistral Voxtral"] CROSS["Cross-validation
Best-of-two"] end PAPA -->|handoff| ANANSI PAPA -->|function call| DEVI_TOOLS OGMA_DUAL -->|transcription| PAPA style PAPA fill:#44337a,stroke:#f59e0b,color:#e2e8f0 style ANANSI fill:#44337a,stroke:#a78bfa,color:#e2e8f0 style DEVI_TOOLS fill:#1b3a2a,stroke:#34d399,color:#e2e8f0 style OGMA_DUAL fill:#1b2e4a,stroke:#818cf8,color:#e2e8f0

4 pre-registered Mistral Agents ยท Conversations for multi-turn ยท Handoffs for delegation ยท Function calling for ElevenLabs tools

๐Ÿ† Track Alignment

ElevenLabs โ€” All 7 Tools in Architecture

%%{init: {"theme": "dark", "themeVariables": {"primaryColor": "#34d399", "primaryTextColor": "#e2e8f0", "lineColor": "#f59e0b", "fontSize": "13px"}}}%% graph LR subgraph INPUT["Input Layer"] MIC["๐ŸŽค Parent Mic"] CHAT["๐Ÿ’ฌ Text Chat"] end subgraph STT_LAYER["โ‘  โ‘ก Speech-to-Text"] S1["โ‘  ElevenAgents
Jerry Concierge
Conversational"] S2["โ‘ก Scribe v1
STT Transcription"] end subgraph VOICE_LAYER["โ‘ข Voice Selection"] S3["โ‘ข Voices/Get API
Browse & Preview"] end subgraph AUDIO_LAYER["โ‘ฃ โ‘ค โ‘ฅ โ‘ฆ Audio Generation"] S4["โ‘ฃ TTS Batch
Multilingual v2
10 languages"] S5["โ‘ค TTS WebSocket
Real-time Streaming"] S6["โ‘ฅ Sound Effects
Contextual SFX"] S7["โ‘ฆ Music Compose
Lullaby Generation"] end subgraph OUTPUT["๐Ÿ”Š 3-Layer Audio"] NAR["Narration"] AMB["Ambience"] MUS["Music Bed"] end MIC --> S2 CHAT --> S1 S1 --> S3 S2 --> S3 S3 --> S4 S3 --> S5 S4 --> NAR S5 --> NAR S6 --> AMB S7 --> MUS style INPUT fill:#1e1b4b,stroke:#818cf8,color:#e2e8f0 style STT_LAYER fill:#1b3a2a,stroke:#34d399,color:#e2e8f0 style VOICE_LAYER fill:#1b3a2a,stroke:#34d399,color:#e2e8f0 style AUDIO_LAYER fill:#1b3a2a,stroke:#34d399,color:#e2e8f0 style OUTPUT fill:#2e1f1b,stroke:#f59e0b,color:#e2e8f0
๐ŸŽช Demo

Live App Demo

Login

Starfield animation. Pre-seeded test accounts in Turso (SQLite cloud, Tokyo region).

PBKDF2-SHA256 password hashing.

๐Ÿ”— Live: sandmantales-api-production.up.railway.app

๐ŸŽช Demo

Create a Story

Sophie's Story

๐ŸŽค Mic button โ†’ Ogma dual-STT
(ElevenLabs + Mistral Voxtral)

๐ŸŒ 10 languages in dropdown

๐Ÿ‘ง Child's name woven into every scene

๐Ÿ“ Parent describes the day in English โ†’ story generated in French

โš™๏ธ Technical๐ŸŽช Demo

Pipeline in Action

9 Agents, Real-Time

๐Ÿ—ฃ๏ธ Ogma transcribes โ†’ โœ“

๐Ÿ“‹ Cache checks SHA-256 โ†’ โœ“

๐ŸŒณ Papa Bois orchestrates via Mistral Agents API โ†’ โœ“

๐Ÿ›ก๏ธ Guardrail validates โ†’ โœ“

๐Ÿ•ท๏ธ Anansi writes story with Mistral Large โ†’ running...

๐Ÿ™ Devi: TTS + SFX + Lullaby โ†’ pending

๐Ÿฆ† Firefly: Illustrations โ†’ pending

โš™๏ธ Technical

Pipeline Complete

All Green โœ…

Every node complete. Story, illustrations, three audio layers generated.


Cache layer: repeat prompts cost zero. SHA-256 dedup on every story + audio clip in Turso.

๐ŸŽช Demo๐Ÿ’ก Creativity

Sophie's Story

๐Ÿ‡ซ๐Ÿ‡ท Sophie et la Baleine de Nuages

๐Ÿ“– Six scenes in French

๐ŸŽจ Watercolour illustrations (Gemini Image Generation)

๐Ÿ”Š Three audio layers:

  • Narration โ€” ElevenLabs Multilingual v2
  • Sound effects โ€” ElevenLabs SFX
  • Lullaby โ€” ElevenLabs Music Compose

๐ŸŽง 10 languages supported

๐ŸŽช Demo

Story Library

18 Stories, 10 Languages

๐Ÿ‡ฌ๐Ÿ‡ง ๐Ÿ‡ซ๐Ÿ‡ท ๐Ÿ‡ฏ๐Ÿ‡ต ๐Ÿ‡ฎ๐Ÿ‡ณ ๐Ÿ‡ช๐Ÿ‡ธ ๐Ÿ‡ต๐Ÿ‡น ๐Ÿ‡ฉ๐Ÿ‡ช ๐Ÿ‡จ๐Ÿ‡ณ ๐Ÿ‡ธ๐Ÿ‡ฆ ๐Ÿ‡ฐ๐Ÿ‡ท

Every story personalised with the child's name and world.


Every night Sophie listens, the stories grow with her. That's not a feature โ€” it's a relationship.

๐Ÿ† Track Alignment

All 7 ElevenLabs Tools

1. ElevenAgents

Jerry โ€” conversational story concierge, helps parents pick voices and themes

2. Speech-to-Text

Ogma โ€” dual STT alongside Voxtral for cross-validation

3. Voices/Get

Voice browser โ€” parents preview narration voices before generating

4. Text-to-Speech

Devi โ€” batch narration across 6 scenes, 10 languages

5. TTS WebSocket

Real-time streaming for scene-by-scene playback

6. Sound Effects

Contextual SFX per scene โ€” ocean waves, birdsong, rain

7. Music Compose

Lullaby generation โ€” gentle music bed under narration
๐Ÿ† Track Alignment

Mistral Integration

Mistral Agents API

Papa Bois orchestrates agent delegation via Conversations + Handoffs

Mistral Large 3

Anansi โ€” story generation, scene splitting, cultural sensitivity

Voxtral

Ogma โ€” speech-to-text alongside ElevenLabs for dual transcription

Vibe CLI

Firefly โ€” built frontend components, Papa Bois planned architecture

%%{init: {"theme": "dark", "themeVariables": {"primaryColor": "#f59e0b", "primaryTextColor": "#e2e8f0", "lineColor": "#a78bfa"}}}%% graph LR V["๐ŸŽค Voxtral STT"] --> PB["๐ŸŒณ Papa Bois
Agents API"] PB --> AN["๐Ÿ•ท๏ธ Anansi
Mistral Large"] PB --> VB["๐Ÿ”ง Vibe CLI
Firefly"] style PB fill:#44337a,stroke:#f59e0b style AN fill:#44337a,stroke:#a78bfa
โš™๏ธ Technical

Engineering Maturity

๐ŸŽจ LoRA Fine-Tuning: Trained Stable Diffusion on 20 storybook images (Gemini Image Generation generated). 500 steps, 15 minutes, 3.1MB weights.


๐Ÿง‘โ€โš–๏ธ LLM-as-Judge: Pixtral evaluated base vs LoRA side-by-side.
Base SD 1.5: 6.8/10 โ†’ LoRA: 9.0/10 โ†’ Gemini Image Generation: 9.5/10


๐Ÿ“Š Decision: We shipped Imagen. Knowing when NOT to use your own model is the innovation.


๐Ÿ’พ Prompt Cache: SHA-256 dedup. Zero-cost repeat requests. All stored in Turso cloud DB.


โœ… 33/33 smoke tests passing โ€” auth, CRUD, cached audio, story gen, all ElevenLabs endpoints, Mistral agents

๐ŸŽฏ Usefulness

Market Opportunity

50M
multilingual households
worldwide
29
languages
supported
$9.99
/month
freemium

Every night Sophie listens, the stories grow with her.
Personalisation data builds a relationship competitors can't copy overnight.

Team ClawCutters

Six mythology-inspired AI agents ยท Seven ElevenLabs tools ยท Mistral Agents API
LoRA fine-tuning ยท Pixtral judge ยท Turso cloud ยท Built in 48 hours


Bonne nuit, Sophie ๐ŸŒ™

๐Ÿ”— sandmantales-api-production.up.railway.app